MétaCan
Menu
Back to cohort
Record W2902154261 · doi:10.1038/s41467-018-07619-7

Why rankings of biomedical image analysis competitions should be interpreted with care

2018· article· en· W2902154261 on OpenAlexaff
Lena Maier‐Hein, Matthias Eisenmann, Annika Reinke, Sinan Onogur, Marko Stankovic, Patrick Godau, Tal Arbel, Hrvoje Bogunović, Andrew P. Bradley, Aaron Carass, Carolin Feldmann, Alejandro F. Frangi, Peter M. Full, Bram van Ginneken, Allan Hanbury, Katrin Honauer, Michal Kozubek, Bennett A. Landman, Keno März, Oskar Maier, Klaus Maier‐Hein, Bjoern Menze, Henning Müller, Peter Neher, Wiro J. Niessen, Nasir Rajpoot, G Sharp, Korsuk Sirinukunwattana, Stefanie Speidel, Christian Stock, Danail Stoyanov, Abdel Aziz Taha, Fons van der Sommen, Ching‐Wei Wang, Marc-André Weber, Guoyan Zheng, Pierre Jannin, Annette Kopp‐Schneider

Bibliographic record

VenueNature Communications · 2018
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsMcGill University
FundersNational Institute of Neurological Disorders and StrokeEngineering and Physical Sciences Research CouncilMedical Research CouncilMinistry of Science and Technology, TaiwanNational Institute of Biomedical Imaging and BioengineeringGrantová Agentura České RepublikyDeutsches KrebsforschungszentrumDeutsche ForschungsgemeinschaftAustralian Research CouncilWellcome TrustSchweizerischer Nationalfonds zur Förderung der Wissenschaftlichen ForschungNational Institutes of HealthNational Science Foundation
KeywordsRanking (information retrieval)Computer scienceRank (graph theory)Data scienceQuality (philosophy)Information retrievalImage (mathematics)Data miningArtificial intelligenceMathematics

Abstract

fetched live from OpenAlex

International challenges have become the standard for validation of biomedical image analysis methods. Given their scientific impact, it is surprising that a critical analysis of common practices related to the organization of challenges has not yet been performed. In this paper, we present a comprehensive analysis of biomedical image analysis challenges conducted up to now. We demonstrate the importance of challenges and show that the lack of quality control has critical consequences. First, reproducibility and interpretation of the results is often hampered as only a fraction of relevant information is typically provided. Second, the rank of an algorithm is generally not robust to a number of variables such as the test data used for validation, the ranking scheme applied and the observers that make the reference annotations. To overcome these problems, we recommend best practice guidelines and define open research questions to be addressed in the future.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.173
metaresearch head score (Gemma)0.564
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Evaluation · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Commentary · Consensus signal: Commentary
Teacher disagreement score0.827
Threshold uncertainty score0.913

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1730.564
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0090.006
Science and technology studies0.0050.009
Scholarly communication0.0200.014
Open science0.0050.006
Research integrity0.0050.007
Insufficient payload (model declined to judge)0.0090.007

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.014
GPT teacher head0.345
Teacher spread0.332 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designTheoretical or conceptual
DomainEvaluation
GenreCommentary

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations367
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueNature CommunicationsSame topicRadiomics and Machine Learning in Medical ImagingFrench-language works237,207